| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009488678820082789, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018977357640165578, | |
| "grad_norm": 0.4039615988731384, | |
| "learning_rate": 1e-05, | |
| "loss": 3.2259, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018977357640165578, | |
| "eval_loss": 5.8987603187561035, | |
| "eval_runtime": 167.1619, | |
| "eval_samples_per_second": 53.092, | |
| "eval_steps_per_second": 26.549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00037954715280331155, | |
| "grad_norm": 0.3469000458717346, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7451, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00037954715280331155, | |
| "eval_loss": 5.894749641418457, | |
| "eval_runtime": 97.1382, | |
| "eval_samples_per_second": 91.365, | |
| "eval_steps_per_second": 45.687, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005693207292049674, | |
| "grad_norm": 0.3894922137260437, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9739, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007590943056066231, | |
| "grad_norm": 0.4525291323661804, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6925, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007590943056066231, | |
| "eval_loss": 5.884451389312744, | |
| "eval_runtime": 97.4136, | |
| "eval_samples_per_second": 91.106, | |
| "eval_steps_per_second": 45.558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009488678820082789, | |
| "grad_norm": 0.3812948167324066, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5259, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 75443831046144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |